AI News

Closing the Modality Gap via Simplex-Constrained Representations (arxiv.org)

LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling (arxiv.org)

Rethinking LoRA Initialization for Robust Asymmetric Learning Rates (arxiv.org)

Beyond Channel Data: Configuration-Enriched Radio Foundation Models (arxiv.org)

DIGOM: Disentangled Interaction Graphs for Outcome prediction in Multimodal healthcare (arxiv.org)

Validating the Comparison, Not Just the Scorer: Why Overall Accuracy Can Mislead in Interactive LLM Evaluation (arxiv.org)

Do Language Models Trust Their Own Justifications? A Study on Functional Consistency (arxiv.org)

FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River (arxiv.org)

DELA: Learning Controllable Edits for Diffusion Language Models (arxiv.org)

What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry (arxiv.org)

TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent (arxiv.org)

SEVI: Safe Evidential Real-World Reinforcement Learning (arxiv.org)

Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control (arxiv.org)

Before the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant (arxiv.org)

Sparsity-driven emergence of functional modularity in multitask neural networks (arxiv.org)

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis (arxiv.org)

Anti-coherence Regularized Absolute Scaling for Out-of-Distribution Detection (arxiv.org)

Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? (arxiv.org)

Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition (arxiv.org)

DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection (arxiv.org)

Distributional Alignment of LLMs and Its Generalization Properties (arxiv.org)

When Clinical Judgment Becomes a Predictive Shortcut: Two Questions Clinical AI Must Answer Before Deployment (arxiv.org)

Training an MoE LLM in MXFP4: How We Closed the Gap to BF16 (arxiv.org)

Behaviour analysis for large language model-driven agents (arxiv.org)

Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation (arxiv.org)

Rethinking Structured Generation: Can Graph-Based Reasoning Resolve Ambiguity? (arxiv.org)

PoKER: A Probability of Kill Estimation Rate Model for Air-to-Air Missiles Using Machine Learning on Stochastic Targets (arxiv.org)

PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers (arxiv.org)

Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use (arxiv.org)

EditJev: System One Routing for Image Editing Models (arxiv.org)

Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting (arxiv.org)

The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study (arxiv.org)

Interpretable Singing Emotion Recognition Using Acoustic and Vocal Technique Features (arxiv.org)

ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation (arxiv.org)

NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding (arxiv.org)

Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs (arxiv.org)

How Ground Truth Shapes Retrieval Scores: Evidence-Aware Evaluation of a Retrieval-Augmented Generation System for Breast Lesions (arxiv.org)

TensorCommitments: A Lightweight Verifiable Inference for Large Language Models (arxiv.org)

Generalized green and red concepts for artificial intelligence, big data, and information and communication technologies: Multidimensional framework and countermeasures (arxiv.org)

Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation (arxiv.org)

Collaborative In-Context Learning for Indoor Radio Map Estimation (arxiv.org)

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction (arxiv.org)

GeoDiv KAN Solver for Time Fractional Navier Stokes Equations on Complex Domains to Realistic CFD Reconstruction (arxiv.org)

Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence (arxiv.org)

Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in Astronomy (arxiv.org)

Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement (arxiv.org)

RSIHub: A Composable Framework for Agent-Evolution Methods (arxiv.org)

Machine-Readable Operator Manuals over the ISO 11783 Network for Offline, Multilingual LLM Assistance (arxiv.org)

Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation (arxiv.org)

Testing Transformer Learnability on the Arithmetic Sequence of Rooted Trees (arxiv.org)